Abstract
Since the multitudinous parameters make the DMFC model become a complex "black-box" direct methanol fuel cell (DMFC) modeling has become an important and difficult issue of practical experiment. This paper presents the model of the small DMFC Bipolar Plate Stack System. This system is different from the conventional complex mathematical models by the neural network (NN) which is considered the real paramneters of the measurement inputs and outputs. First the training data is the power density of short-term stability tests for the DMFC 10-cell stacks. Then the DMFC model can be obtained by NN method and contented to the different unit cell stacks. Finally, the simulation results in agreement with experimnental results show that the NN modeling method effectively projects the power density on small DMFC packs, such as the developmnent and simulation tool. Therefore the NN modeling method can save much time to reform the conventional mathematical models by the very expensive experimnent.
| Original language | English |
|---|---|
| Pages (from-to) | 4765-4774 |
| Number of pages | 10 |
| Journal | International Journal of Innovative Computing, Information and Control |
| Volume | 5 |
| Issue number | 12 |
| Publication status | Published - 2009 Dec 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computational Theory and Mathematics
- Information Systems
- Software
- Theoretical Computer Science
Cite this
}
Neural network modeling for small DMFC bipolar plate stack system. / Chen, Hwa Chaing; Hsu, Chao Hsing; Chou, Pao Hua; Yang, Shu Han; Chang, Chi Yuan; Wu, Menq-Jiun.
In: International Journal of Innovative Computing, Information and Control, Vol. 5, No. 12, 01.12.2009, p. 4765-4774.Research output: Contribution to journal › Article
TY - JOUR
T1 - Neural network modeling for small DMFC bipolar plate stack system
AU - Chen, Hwa Chaing
AU - Hsu, Chao Hsing
AU - Chou, Pao Hua
AU - Yang, Shu Han
AU - Chang, Chi Yuan
AU - Wu, Menq-Jiun
PY - 2009/12/1
Y1 - 2009/12/1
N2 - Since the multitudinous parameters make the DMFC model become a complex "black-box" direct methanol fuel cell (DMFC) modeling has become an important and difficult issue of practical experiment. This paper presents the model of the small DMFC Bipolar Plate Stack System. This system is different from the conventional complex mathematical models by the neural network (NN) which is considered the real paramneters of the measurement inputs and outputs. First the training data is the power density of short-term stability tests for the DMFC 10-cell stacks. Then the DMFC model can be obtained by NN method and contented to the different unit cell stacks. Finally, the simulation results in agreement with experimnental results show that the NN modeling method effectively projects the power density on small DMFC packs, such as the developmnent and simulation tool. Therefore the NN modeling method can save much time to reform the conventional mathematical models by the very expensive experimnent.
AB - Since the multitudinous parameters make the DMFC model become a complex "black-box" direct methanol fuel cell (DMFC) modeling has become an important and difficult issue of practical experiment. This paper presents the model of the small DMFC Bipolar Plate Stack System. This system is different from the conventional complex mathematical models by the neural network (NN) which is considered the real paramneters of the measurement inputs and outputs. First the training data is the power density of short-term stability tests for the DMFC 10-cell stacks. Then the DMFC model can be obtained by NN method and contented to the different unit cell stacks. Finally, the simulation results in agreement with experimnental results show that the NN modeling method effectively projects the power density on small DMFC packs, such as the developmnent and simulation tool. Therefore the NN modeling method can save much time to reform the conventional mathematical models by the very expensive experimnent.
UR - http://www.scopus.com/inward/record.url?scp=74349093770&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=74349093770&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:74349093770
VL - 5
SP - 4765
EP - 4774
JO - International Journal of Innovative Computing, Information and Control
JF - International Journal of Innovative Computing, Information and Control
SN - 1349-4198
IS - 12
ER -